{"id":"W6891628535","doi":"10.48448/n5hs-z234","title":"CODER: An efficient framework for improving retrieval through COntextual Document Embedding Reranking","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Embedding; Relevance (law); Document retrieval; Set (abstract data type); Ranking (information retrieval); Context (archaeology); Encoder; Training set","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001481709,0.00170554,0.001539159,0.002304888,0.0004583243,0.001127281,0.001963685,0.001270368,0.004981064],"category_scores_gemma":[0.005223363,0.0004827264,0.0007082205,0.001578035,0.0006073954,0.002700359,0.00158049,0.001619093,0.005404877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007153408,"about_ca_system_score_gemma":0.001212695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007256956,"about_ca_topic_score_gemma":0.01501519,"domain_scores_codex":[0.9990491,0.0002429612,0.00005236607,0.0002415586,0.0003233472,0.00009059321],"domain_scores_gemma":[0.9988565,0.0003681605,0.00009351406,0.0003268995,0.000294544,0.00006038792],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002814961,0.0002866214,0.0009144354,0.000374958,0.0001077413,0.0001448558,0.0001219866,0.06834513,0.03770151,0.009310347,0.03248893,0.8499219],"study_design_scores_gemma":[0.00008692104,0.000205806,0.0003711659,0.00002124969,0.00003645818,0.0002039494,0.00003249053,0.9618469,0.01677108,0.009328448,0.0110526,0.00004300184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01154771,0.001170865,0.9652991,0.0002244122,0.0001025239,0.0001888032,0.0007151177,0.01901361,0.001737892],"genre_scores_gemma":[0.1491187,0.0007125754,0.8385546,0.0002967603,0.0002408772,0.0002965982,0.003586996,0.001213341,0.005979551],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007256956,"threshold_uncertainty_score":0.01666331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03348975065760965,"score_gpt":0.3583281650714972,"score_spread":0.3248384144138875,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}